nascan部分的結構:
lib
init.py
cider.py: CIDR形式IP地址解析;
common.py: 其它方法;
icmp.py: ICMP消息發送類;
log.py: 控制檯信息輸出;
mongo.py: 數據庫連接;
scan.py: 掃描與識別;
start.py: 線程控制;
plugin
masscan.py :masscan調用腳本;
nascan.py: 網絡資產信息抓取引擎;
nascan代碼分析
import thread
from lib.common import *
from lib.start import *
if __name__ == "__main__":
try:
CONFIG_INI = get_config() # 讀取配置,讀取數據庫中整個Config集合數據
log.write('info', None, 0, u'獲取配置成功')#輸出到控制檯
STATISTICS = get_statistics() # 讀取統計信息
MASSCAN_AC = [0] #值爲1表示masscan正在掃描
NACHANGE = [0] #值爲1表示能進入掃描階段
thread.start_new_thread(monitor, (CONFIG_INI, STATISTICS, NACHANGE)) # 心跳線程
thread.start_new_thread(cruise, (STATISTICS, MASSCAN_AC)) # 失效記錄刪除線程
socket.setdefaulttimeout(int(CONFIG_INI['Timeout']) / 2) # 設置連接超時
ac_data = []
while True:
now_time = time.localtime()
now_hour = now_time.tm_hour
now_day = now_time.tm_mday
now_date = str(now_time.tm_year) + \
str(now_time.tm_mon) + str(now_day)
cy_day, ac_hour = CONFIG_INI['Cycle'].split('|')
log.write('info', None, 0, u'掃描規則: ' + str(CONFIG_INI['Cycle']))#log.write()函數,格式化了輸出在控制檯界面的信息,並使用了線程鎖,防止信息一時間輸出過多,導致顯示錯行。
# 判斷是否進入掃描時段或者能直接進入掃描階段
if (now_hour == int(ac_hour) and now_day % int(cy_day) == 0 and now_date not in ac_data) or NACHANGE[0]:
ac_data.append(now_date)
#恢復原值,不能再次進入資產探測,直到新的事件觸發該值改變
NACHANGE[0] = 0
log.write('info', None, 0, u'開始掃描')
# 具體的資產發現操作
s = start(CONFIG_INI)
# masscan掃描狀態
s.masscan_ac = MASSCAN_AC
s.statistics = STATISTICS
s.run()
time.sleep(60)
except Exception, e:
print e
1、CONFIG_INI = get_config() # 讀取配置,讀取數據庫中整個Config集合數據
讀取配置,get_config()進去
nascan/lib/common.py
# 信息識別Config集合, 配置統一格式化,返回dict類型
def get_config():
config = {}
# Config集合共有vulscan、nascan兩個子集合,獲取Config集合中的nascan子集合的文檔內容
config_info = mongo.na_db.Config.find_one({"type": "nascan"})
for name in config_info['config']:
if name in ['Discern_cms', 'Discern_con', 'Discern_lang', 'Discern_server']:
''' cms識別、組件容器識別、語言技術識別、端口服務識別四個部分的文檔內容賦值配按照
事先定義的格式進一步格式化分離數據,
方便後續取用. '''
config[name] = format_config(name, config_info['config'][name]['value'])
else:
config[name] = config_info['config'][name]['value']
return config
- 讀取了mongodb裏面的Config集合中的nascan子集合的文檔內容;
2、get_statistics()讀取統計信息返回時間
位於nascan/lib/common.py
def get_statistics():
date_ = datetime.datetime.now().strftime('%Y-%m-%d')
now_stati = mongo.na_db.Statistics.find_one({"date": date_})
if not now_stati:
now_stati = {date_: {"add": 0, "update": 0, "delete": 0}}
return now_stati
else:
return {date_: now_stati['info']}
3、 MASSCAN_AC = [0] #值爲1表示masscan正在掃描
NACHANGE = [0] #值爲1表示能進入掃描階段
4、
thread.start_new_thread(monitor, (CONFIG_INI, STATISTICS, NACHANGE)) # 心跳線程
thread.start_new_thread(cruise, (STATISTICS, MASSCAN_AC)) # 失效記錄刪除線程
socket.setdefaulttimeout(int(CONFIG_INI['Timeout']) / 2) # 設置連接超時
- monitor–心跳線程
位於nascan/lib/common.py
def monitor(CONFIG_INI, STATISTICS, NACHANGE):
while True:#線程通過While True和設定延時,實現了監控資產列表,定時更新數據庫、觸發掃描、清理失效目標等操作。
try:
time_ = datetime.datetime.now()
date_ = time_.strftime('%Y-%m-%d')
mongo.na_db.Heartbeat.update({"name": "heartbeat"}, {"$set": {"up_time": time_}})
if date_ not in STATISTICS: STATISTICS[date_] = {"add": 0, "update": 0, "delete": 0}
mongo.na_db.Statistics.update({"date": date_}, {"$set": {"info": STATISTICS[date_]}}, upsert=True)
new_config = get_config()#獲取數據庫最新的config集合數據
if base64.b64encode(CONFIG_INI["Scan_list"]) != base64.b64encode(new_config["Scan_list"]):NACHANGE[0] = 1# 比較掃描目標是否發生了變化, 變化就將值置爲1, 表示需要重新掃描
CONFIG_INI.clear()
CONFIG_INI.update(new_config)
except Exception, e:
print e
time.sleep(30)
再一次調用get_config()獲取數據庫config集合中最新的數據;
如果scan_list的base的值發生變化,則將NACHANGE[0] = 1,更新config,重新進行掃描;
- cruise–失效刪除記錄
位於nascan/lib/common.py
def cruise(STATISTICS,MASSCAN_AC):
while True:
now_str = datetime.datetime.now()
week = int(now_str.weekday())
hour = int(now_str.hour)
if week >= 1 and week <= 5 and hour >= 9 and hour <= 18: # 非工作時間不刪除
try:
data = mongo.NA_INFO.find().sort("time", 1)
for history_info in data:
while True:
if MASSCAN_AC[0]: # 如果masscan正在掃描即不進行清理
time.sleep(10)
else:
break
ip = history_info['ip']
port = history_info['port']
try:
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)#對目標(ip:port)進行sock連接
sock.connect((ip, int(port)))
sock.close()
except Exception, e:
time_ = datetime.datetime.now()
date_ = time_.strftime('%Y-%m-%d')
mongo.NA_INFO.remove({"ip": ip, "port": port})#進行sock連接,連接不上就刪除數據庫INFO裏面的ip和port
log.write('info', None, 0, '%s:%s delete' % (ip, port))
STATISTICS[date_]['delete'] += 1
del history_info["_id"]
history_info['del_time'] = time_#然後將刪除時間寫入history_info
history_info['type'] = 'delete'
mongo.NA_HISTORY.insert(history_info)
except:
pass
time.sleep(3600)
對目標(ip:port)進行sock連接,如果連接不上就刪除數據庫INFO裏面的ip和port,然後將刪除時間寫入history_info;
5、log.write('info', None, 0, u'掃描規則: ' + str(CONFIG_INI['Cycle']))
log.write()函數,格式化了輸出在控制檯界面的信息;
6、if (now_hour == int(ac_hour) and now_day % int(cy_day) == 0 and now_date not in ac_data) or NACHANGE[0]:
ac_data.append(now_date)
如果到達掃描的週期時間或者如果NACHANGE[0]的值爲1,任何一個成立都可以重新掃描;
7、s = start(CONFIG_INI)
進入start()函數,位於nascan/lib/start.py
class start:
def __init__(self, config): # 默認配置
self.config_ini = config
self.queue = Queue.Queue()
self.thread = int(self.config_ini['Thread'])
self.scan_list = self.config_ini['Scan_list'].split('\n')
self.mode = int(self.config_ini['Masscan'].split('|')[0])
self.icmp = int(self.config_ini['Port_list'].split('|')[0])
self.white_list = self.config_ini.get('White_list', '').split('\n')
def run(self):
global AC_PORT_LIST
all_ip_list = []
for ip in self.scan_list:
# 解析CIDR形式IP地址
if "/" in ip:
ip = cidr.CIDR(ip)
if not ip:
continue
# 獲得完整目標IP地址列表
ip_list = self.get_ip_list(ip)
for white_ip in self.white_list:
if white_ip in ip_list:
ip_list.remove(white_ip)
# 當使用masscan掃描時
if self.mode == 1:#判斷是否支持masscan掃描
masscan_path = self.config_ini['Masscan'].split('|')[2]
masscan_rate = self.config_ini['Masscan'].split('|')[1]
# 如果用戶在前臺關閉了ICMP存活探測則進行全IP段掃描
if self.icmp:
ip_list = self.get_ac_ip(ip_list) # 默認使用icmp去探測獲得存活主機
self.masscan_ac[0] = 1 # 可以繼續masscan端口掃描
# 如果安裝了Masscan即使用Masscan進行全端口掃描
AC_PORT_LIST = self.masscan(
ip_list, masscan_path, masscan_rate)
if not AC_PORT_LIST:
continue
self.masscan_ac[0] = 0 #不能再次用masscan進行端口掃描
for ip_str in AC_PORT_LIST.keys():
self.queue.put(ip_str) # ip地址加入隊列
self.scan_start() # 開始掃描 開始端口banner獲取和banner比對識別等
else:
all_ip_list.extend(ip_list)
# 不使用masscan時
if self.mode == 0:
# 如果啓用存活主機探測功能時,會用icmp echo探測存活的主機ip
if self.icmp:
all_ip_list = self.get_ac_ip(all_ip_list)
# IP地址加入隊列
for ip_str in all_ip_list:
self.queue.put(ip_str) # 加入隊列
self.scan_start() # TCP探測模式開始掃描
if self.mode == 1 判斷是否支持masscan掃描,如果支持就使用Masscan進行全端口掃描。如果沒有開啓,將ip添加到all_ip_list這個列表中。
masscan函數
位於nascan/lib/start.py
def masscan(self, ip, masscan_path, masscan_rate):
try:
if len(ip) == 0:
return
sys.path.append(sys.path[0] + "/plugin")
m_scan = __import__("masscan")#動態加載plugin目錄下的masscan
result = m_scan.run(ip, masscan_path, masscan_rate)
return result
except Exception, e:
print e
print 'No masscan plugin detected'
動態加載plugin目錄下的masscan.py
masscan.py
def run(ip_list,path,rate):
try:
ip_file = open('target.log','w')
ip_file.write("\n".join(ip_list))
ip_file.close()
# 過濾可能導致命令執行的字符,過濾了;|&這三個字符
path = str(path).translate(None, ';|&`\n')
rate = str(rate).translate(None, ';|&`\n')
if not os.path.exists(path):return
# 將path、rate加到命令後面執行
os.system("%s -p1-65535 -iL target.log -oL tmp.log --randomize-hosts --rate=%s"%(path,rate))
result_file = open('tmp.log', 'r')
result_json = result_file.readlines()
result_file.close()
del result_json[0]
del result_json[-1]
open_list = {}
for res in result_json:
try:
ip = res.split()[3]
port = res.split()[2]
if ip in open_list:
open_list[ip].append(port)
else:
open_list[ip] = [port]
except:pass
os.remove('target.log')
os.remove('tmp.log')
return open_list
except:
pass
先過濾可能導致命令執行的字符,過濾了;|&這三個字符;
然後將 將path、rate加到命令後面執行;
將掃描結果保存在tmp.log文件然後讀取裏面的內容;
8、scan_start()函數
不管有沒有使用masscan掃描都會進入scan_start()函數,開始進行掃描;
def scan_start(self):
for i in range(self.thread): # 開始掃描
t = ThreadNum(self.queue)
t.setDaemon(True)
t.mode = self.mode
t.config_ini = self.config_ini#提供配置信息
t.statistics = self.statistics#提供統計信息
t.start()
self.queue.join()
進入ThreadNum中
class ThreadNum(threading.Thread):
def __init__(self, queue):
threading.Thread.__init__(self)
self.queue = queue
#run()函數,把IP地址和端口號列表傳到另一個scan()函數中
def run(self):
while True:
try:
# ip地址隊列
task_host = self.queue.get(block=False)
except:
break
try:
# 如果使用masscan, 端口就用掃描到的已經開放的端口
if self.mode:
port_list = AC_PORT_LIST[task_host]
# 沒有使用masscan, 使用默認端口
else:
port_list = self.config_ini['Port_list'].split('|')[
1].split('\n')
# 根據banner識別端口開放的服務
_s = scan.scan(task_host, port_list)
_s.config_ini = self.config_ini
_s.statistics = self.statistics # 提供統計信# 提供配置信息
_s.run()
except Exception, e:
print e
finally:
self.queue.task_done()
_s = scan.scan(task_host, port_list)
這裏ip地址和端口號傳入到另一個scan函數中;
scan()函數
位於/nascan/lib/scan.py
class scan:
def __init__(self, task_host, port_list):
self.ip = task_host
self.port_list = port_list
self.config_ini = {}
def run(self):
self.timeout = int(self.config_ini['Timeout'])
for _port in self.port_list:
self.server = ''
self.banner = ''
self.port = int(_port)
# 基礎單端口掃描獲得開放端口banner
self.scan_port() # 端口掃描
if not self.banner:
continue
self.server_discern() #服務識別 使用獲得的banner進行服務類型識別
# 測試還剩下的一些沒識別出來的端口服務是不是web服務器
if self.server == '':
web_info = self.try_web() # 嘗試web訪問
if web_info:
log.write('web', self.ip, self.port, web_info)
time_ = datetime.datetime.now()
# Info 集合更新
mongo.NA_INFO.update({'ip': self.ip, 'port': self.port},
{"$set": {'banner': self.banner, 'server': 'web', 'webinfo': web_info,
'time': time_}})
scan的run()函數先進行了端口掃描,然後進入server_discern()函數。
self.scan_port() # 端口掃描
def scan_port(self):
try:
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
sock.connect((self.ip, self.port))
time.sleep(0.2)
except Exception, e:
return
try:
self.banner = sock.recv(1024)
sock.close()
if len(self.banner) <= 2:
self.banner = 'NULL'
except Exception, e:
self.banner = 'NULL'
log.write('portscan', self.ip, self.port, None)
banner = ''
hostname = self.ip2hostname(self.ip)
time_ = datetime.datetime.now()
date_ = time_.strftime('%Y-%m-%d')
try:
banner = unicode(self.banner, errors='replace')
if self.banner == 'NULL':
banner = ''
mongo.NA_INFO.insert({"ip": self.ip, "port": self.port,
"hostname": hostname, "banner": banner, "time": time_})
self.statistics[date_]['add'] += 1
except:
if banner:
history_info = mongo.NA_INFO.find_and_modify(
query={"ip": self.ip, "port": self.port, "banner": {"$ne": banner}}, remove=True)
if history_info:
mongo.NA_INFO.insert(
{"ip": self.ip, "port": self.port, "hostname": hostname, "banner": banner, "time": time_})
self.statistics[date_]['update'] += 1
del history_info["_id"]
history_info['del_time'] = time_
history_info['type'] = 'update'
mongo.NA_HISTORY.insert(history_info)
scan_port()通過socket套接字連接,獲得端口服務返回的banner信息;
self.server_discern() #服務識別 使用獲得的banner進行服務類型識別
進入server_discern()函數
def server_discern(self):
for mark_info in self.config_ini['Discern_server']: # 快速識別
try:
# 服務名默認端口識別方法 banner匹配正則表達式
name, default_port, mode, reg = mark_info
# 識別模式是default的,只判斷端口號
if mode == 'default':
if int(default_port) == self.port:
self.server = name
# 識別模式是banner的,正則匹配banner
elif mode == 'banner':
matchObj = re.search(reg, self.banner, re.I | re.M)#re.M多行匹配,影響 ^ 和 $; re.I使匹配對大小寫不敏感;
if matchObj:
self.server = name
if self.server:
break
except:
continue
# 處理沒識別出來的也不太像(不嚴謹)web的服務
if not self.server and self.port not in [80, 443, 8080]:
for mark_info in self.config_ini['Discern_server']: # 發包識別
try:
name, default_port, mode, reg = mark_info
if mode not in ['default', 'banner']:
dis_sock = socket.socket(
socket.AF_INET, socket.SOCK_STREAM)
dis_sock.connect((self.ip, self.port))
mode = mode.decode('string_escape')
reg = reg.decode('string_escape')
dis_sock.send(mode)
time.sleep(0.3)
dis_recv = dis_sock.recv(1024)
dis_sock.close()
matchObj = re.search(reg, dis_recv, re.I | re.M)
if matchObj:
self.server = name
break
except:
pass
if self.server:
log.write("server", self.ip, self.port, self.server)
mongo.NA_INFO.update({"ip": self.ip, "port": self.port}, {
"$set": {"server": self.server}})
server_discern()函數,通過正則表達式,依次比較,獲得服務類型;
- try_web()函數
def try_web(self):
title_str, html = '', ''
try:
if self.port == 443:
info = urllib2.urlopen("https://%s:%s" %
(self.ip, self.port), timeout=self.timeout)
else:
info = urllib2.urlopen("http://%s:%s" %
(self.ip, self.port), timeout=self.timeout)
html = info.read()
header = info.headers
except urllib2.HTTPError, e:
html = e.read()
header = e.headers
except:
return
if not header:
return
# 解壓gzip
if 'Content-Encoding' in header and 'gzip' in header['Content-Encoding']:
html_data = StringIO.StringIO(html)
gz = gzip.GzipFile(fileobj=html_data)
html = gz.read()
try:
html_code = self.get_code(header, html).strip()
if html_code and len(html_code) < 12:
html = html.decode(html_code).encode('utf-8')
except:
pass
try:
title = re.search(r'<title>(.*?)</title>', html, flags=re.I | re.M)
if title:
title_str = title.group(1)
except:
pass
try:
web_banner = str(header) + "\r\n\r\n" + html
self.banner = web_banner
history_info = mongo.NA_INFO.find_one(
{"ip": self.ip, "port": self.port})
if 'server' not in history_info:
tag = self.get_tag()
web_info = {'title': title_str, 'tag': tag}
return web_info
else:
if abs(len(history_info['banner'].encode('utf-8')) - len(web_banner)) > len(web_banner) / 60:
del history_info['_id']
history_info['del_time'] = datetime.datetime.now()
mongo.NA_HISTORY.insert(history_info)
tag = self.get_tag()
web_info = {'title': title_str, 'tag': tag}
date_ = datetime.datetime.now().strftime('%Y-%m-%d')
self.statistics[date_]['update'] += 1
log.write('info', None, 0, '%s:%s update web info' %
(self.ip, self.port))
return web_info
except:
return
nascan代碼大致流程